{"data":{"slug":"suno-ai-bark","name":"bark","tagline":"Text-Prompted Generative Audio Model","github_url":"https://github.com/suno-ai/bark","owner":"suno-ai","repo":"bark","owner_avatar_url":"https://avatars.githubusercontent.com/u/99442120?v=4","primary_language":"Jupyter Notebook","stars":39272,"forks":4669,"topics":[],"archived":false,"github_pushed_at":"2024-08-19T07:45:36+00:00","maintenance_label":"Dormant","stars_delta_30d":54,"url":"https://www.graphcanon.com/tools/suno-ai-bark","markdown_url":"https://www.graphcanon.com/tools/suno-ai-bark.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/suno-ai-bark","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=suno-ai-bark","description":"🔊 Text-Prompted Generative Audio Model","homepage_url":null,"license":"MIT","open_issues":268,"watchers":333,"ai_summary":"Bark is a text-to-speech model that generates audio from text prompts. It supports both CPU and GPU inference, with varying performance based on hardware capabilities.","readme_excerpt":"## 💻 Installation\n*‼️ CAUTION ‼️ Do NOT use `pip install bark`. It installs a different package, which is not managed by Suno.*\n```bash\npip install git+https://github.com/suno-ai/bark.git\n```\n\nor\n\n```bash\ngit clone https://github.com/suno-ai/bark\ncd bark && pip install . \n```\n\n---\n\n## 🛠️ Hardware and Inference Speed\n\nBark has been tested and works on both CPU and GPU (`pytorch 2.0+`, CUDA 11.7 and CUDA 12.0).\n\nOn enterprise GPUs and PyTorch nightly, Bark can generate audio in roughly real-time. On older GPUs, default colab, or CPU, inference time might be significantly slower. For older GPUs or CPU you might want to consider using smaller models. Details can be found in out tutorial sections here.\n\nThe full version of Bark requires around 12GB of VRAM to hold everything on GPU at the same time. \nTo use a smaller version of the models, which should fit into 8GB VRAM, set the environment flag `SUNO_USE_SMALL_MODELS=True`.\n\nIf you don't have hardware available or if you want to play with bigger versions of our models, you can also sign up for early access to our model playground [here](https://suno-ai.typeform.com/suno-studio).\n\n---\n\n## © License\n\nBark is licensed under the MIT License.","github_created_at":"2023-04-07T19:34:48+00:00","created_at":"2026-07-11T23:09:35.688778+00:00","updated_at":"2026-09-20T04:29:27.368761+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"audio-generation","name":"audio-generation"},{"slug":"cpu","name":"cpu"},{"slug":"generative-model","name":"generative-model"},{"slug":"gpu","name":"gpu"},{"slug":"hardware-requirements","name":"hardware requirements"},{"slug":"inference-speed","name":"inference speed"},{"slug":"pytorch","name":"pytorch"},{"slug":"text-to-speech","name":"text-to-speech"}],"trust":{"provenance":{"is_fork":false,"github_id":624994625,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:15:50.013Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":760,"last_release_at":null,"stars_delta_30d":54,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:15:52.180Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:15:48.934Z"},"languages":{"value":["jupyter notebook","python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:15:48.934Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:15:48.934Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["Use Bark when you need to generate audio from text prompts and have access to hardware with at least 8GB of VRAM for smaller models or 12GB for the full version.","Consider Bark if you are working with PyTorch 2.0+ and CUDA 11.7 or 12.0, as it can generate audio in real-time on enterprise GPUs.","Opt for Bark when you want to experiment with text-to-speech capabilities in a Jupyter Notebook environment."],"when_not_to_use":["Avoid Bark if your hardware is limited to older GPUs or CPUs, as inference times might be significantly slower, impacting productivity.","Do not use Bark if you require a package installed via `pip install bark`, as this installs a different package not managed by Suno.","Bark may not be suitable if you need a text-to-speech solution that does not require setting up an environment flag for smaller models to fit into 8GB VRAM."],"source":"enrich:decision_facts","observed_at":"2026-09-18T10:24:44.596Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"Bark is a text-to-speech model that generates audio from text prompts, supporting both CPU and GPU inference with varying performance based on hardware capabilities."}]}}